CN109084350B - Range hood with optical filtering function visual detection module and range hood concentration detection method - Google Patents
Range hood with optical filtering function visual detection module and range hood concentration detection method Download PDFInfo
- Publication number
- CN109084350B CN109084350B CN201811151666.1A CN201811151666A CN109084350B CN 109084350 B CN109084350 B CN 109084350B CN 201811151666 A CN201811151666 A CN 201811151666A CN 109084350 B CN109084350 B CN 109084350B
- Authority
- CN
- China
- Prior art keywords
- image
- visual detection
- detection module
- initial
- gray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 117
- 230000000007 visual effect Effects 0.000 title claims abstract description 87
- 238000001914 filtration Methods 0.000 title claims abstract description 57
- 230000003287 optical effect Effects 0.000 title claims abstract description 26
- 239000000779 smoke Substances 0.000 claims abstract description 84
- 238000000034 method Methods 0.000 claims abstract description 45
- 230000001502 supplementing effect Effects 0.000 claims abstract description 38
- 238000003384 imaging method Methods 0.000 claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims description 47
- 230000006870 function Effects 0.000 claims description 29
- 230000007797 corrosion Effects 0.000 claims description 21
- 238000005260 corrosion Methods 0.000 claims description 21
- 238000011179 visual inspection Methods 0.000 claims description 17
- 238000003708 edge detection Methods 0.000 claims description 12
- 235000019504 cigarettes Nutrition 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000009434 installation Methods 0.000 claims description 9
- 239000006233 lamp black Substances 0.000 claims description 5
- 230000008030 elimination Effects 0.000 claims description 4
- 238000003379 elimination reaction Methods 0.000 claims description 4
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 239000006096 absorbing agent Substances 0.000 claims description 2
- 206010070834 Sensitisation Diseases 0.000 claims 7
- 230000008313 sensitization Effects 0.000 claims 7
- 238000011897 real-time detection Methods 0.000 abstract description 4
- 239000013589 supplement Substances 0.000 abstract 1
- WAZUWHGJMMZVHH-UHFFFAOYSA-N 1,2,3-trichloro-5-(2,6-dichlorophenyl)benzene Chemical compound ClC1=C(Cl)C(Cl)=CC(C=2C(=CC=CC=2Cl)Cl)=C1 WAZUWHGJMMZVHH-UHFFFAOYSA-N 0.000 description 9
- 239000003517 fume Substances 0.000 description 4
- 238000011202 physical detection method Methods 0.000 description 4
- 239000004071 soot Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000003595 mist Substances 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000005086 pumping Methods 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F24—HEATING; RANGES; VENTILATING
- F24C—DOMESTIC STOVES OR RANGES ; DETAILS OF DOMESTIC STOVES OR RANGES, OF GENERAL APPLICATION
- F24C15/00—Details
- F24C15/20—Removing cooking fumes
- F24C15/2021—Arrangement or mounting of control or safety systems
Abstract
The range hood with the optical filtering function visual detection module is provided with a hood main body and a visual detection module for detecting the size of the oil smoke, wherein the visual detection module is electrically connected with the hood main body; the visual detection module is provided with a filtering part for filtering visible light and a visual detection part, the filtering part is assembled on the visual detection part, the visual detection part is electrically connected with the smoke machine main body, and the visual detection module faces the corresponding stove area. The visual detection module can filter visible light and simultaneously adopts the light supplementing device to supplement light, so that the interference problem caused by a natural light source and a stroboscopic light source can be eliminated, the interference on shadows and the like can be better achieved, and meanwhile, the size of smoke can be detected without turning on the lamp under bad lighting conditions such as cloudy days and the like. The oil smoke concentration detection method is characterized in that a visual detection module processes an initial image of a front frame and a rear frame which are acquired by imaging equipment as a basis, the initial image is a gray level image, and meanwhile, non-contact real-time detection of the oil smoke concentration can be realized, so that the method has the advantages of high accuracy, real-time performance and the like.
Description
Technical Field
The invention relates to the field of range hoods, in particular to a range hood with a visual detection module with a light filtering function and a range hood concentration detection method.
Background
The vision system of lampblack absorber needs stable light source, and natural light is mainly visible light, because the volatility of visible light is great, when different environment such as overcast day, evening, causes the vision system suitability weak easily, adopts ordinary gaze lamp to be lighting system to among the prior art, also can cause the vision system to gather the luminance existence difference between the preceding frame of image and the back frame, and brings into some external interference easily, and then causes smoke detection or other functions of vision system to produce erroneous judgement.
In the prior art, aiming at the detection of the kitchen fume concentration, an infrared projection method and a physical detection method are mainly adopted. The infrared projection method is used for emitting infrared light through one end and receiving the infrared light through the other end, and the oil smoke concentration is judged through the intensity of the received infrared light. However, because the fume is scattered with uncertainty, interference such as shielding by hands of people can be generated in practice, so that a plurality of infrared transmitters are arranged at different positions to ensure the relative accuracy of fume detection, the cost is high, and the requirement on the installation position is high. The physical detection method is similar to the principle of a smoke alarm, and the oil smoke concentration is judged by detecting the number of floating particles in the air, but the method has two defects, namely, the detection can be carried out only when the oil smoke contacts the alarm, and the remote detection can not be realized; secondly, when the air floats in the air, the oil smoke is not the water mist, and the water mist cannot be detected.
Therefore, in order to solve the deficiencies of the prior art, it is necessary to provide a range hood with a visual detection module having a light filtering function and a method for detecting the concentration of the oil smoke.
Disclosure of Invention
One of the purposes of the present invention is to provide a range hood with a visual detection module having a filtering function, which avoids the shortcomings of the prior art. The range hood with the optical filtering function visual detection module has high anti-interference capability.
The above object of the present invention is achieved by the following technical measures:
the utility model provides a range hood that has filtering function vision detection module is provided with the cigarette machine main part and is used for detecting the vision detection module of oil smoke size, and vision detection module is connected with cigarette machine main part electricity.
The visual detection module is provided with a filtering part for filtering visible light and a visual detection part, the filtering part is assembled on the visual detection part, the visual detection part is electrically connected with the smoke machine main body, and the visual detection module faces the corresponding stove area.
The range hood with the visual detection module with the light filtering function is further provided with a light supplementing device for supplementing light to the corresponding range area, wherein the light supplementing device is electrically connected with the main body of the range hood, and the light supplementing device faces to the corresponding range area.
Preferably, the light supplementing device is an infrared light supplementing device.
The visual detection module is assembled on the main body of the cigarette machine; or alternatively
The visual detection module is assembled on the stove; or alternatively
The visual detection module is assembled on the wall body.
The light supplementing device is assembled on the main body of the cigarette machine; or alternatively
The light supplementing device is assembled on the stove; or alternatively
The light supplementing device is assembled on the wall body.
Preferably, the filter unit is a visible light filter.
Preferably, the light supplementing device is an infrared lamp set with the wavelength of 940 nm.
Preferably, the light supplementing device is set to be an infrared lamp group.
Preferably, the visual detection module processes and sequences the acquired initial images, and processes the initial images of the rear frames and the initial images of the front frames in sequence to obtain the current kitchen oil smoke concentration at the moment when the initial images of the rear frames are located.
Preferably, the infrared lamp sets are provided with a plurality of groups.
Preferably, the visual inspection portion is provided with a lens, a telescopic frame for setting a focal length, a mounting base, a photosensitive chip and a PCB board, the lens is fixedly assembled on the telescopic frame, the telescopic frame is assembled on the mounting base, the photosensitive chip is welded on the PCB board, the mounting base is assembled on the PCB board, the light filtering portion is assembled above the photosensitive chip, and the lens, the telescopic frame, the mounting base, the light filtering portion, the photosensitive chip and the PCB board are sequentially arranged from top to bottom.
Preferably, the visual inspection unit is provided with a lens, a telescopic frame for setting a focal length, a mounting base, a photosensitive chip and a PCB board, the light filtering unit is assembled above the lens, the lens is fixedly assembled on the telescopic frame, the telescopic frame is assembled on the mounting base, the photosensitive chip is welded on the PCB board, the mounting base is assembled on the PCB board, and the light filtering unit, the lens, the telescopic frame, the mounting base, the photosensitive chip and the PCB board are sequentially assembled from top to bottom.
The range hood with the optical filtering function visual detection module is provided with a hood main body and a visual detection module for detecting the size of oil smoke, wherein the visual detection module is electrically connected with the hood main body; the visual detection module is provided with a filtering part for filtering visible light and a visual detection part, the filtering part is assembled on the visual detection part, the visual detection part is electrically connected with the smoke machine main body, and the visual detection module faces the corresponding stove area. The visual detection module can filter visible light and perform light filling by adopting the light filling device, can eliminate the interference problem caused by a natural light source and a stroboscopic light source, has a good effect on interference of shadows and the like, and can detect the size of smoke without turning on a lamp under bad lighting conditions such as cloudy days and the like.
Another object of the present invention is to provide a method for detecting the concentration of soot, which avoids the drawbacks of the prior art. The oil smoke concentration detection method has the characteristics of real-time detection and high accuracy of oil smoke concentration detection results.
The method for detecting the oil smoke concentration comprises the steps that the oil smoke machine with the optical filtering function visual detection module is provided, the visual detection module takes an initial image collected by imaging equipment as a basis for processing, the initial image is a gray level image, the collected initial image is serialized, and the current oil smoke concentration of a kitchen at the moment when each initial image of a rear frame is located is obtained through processing the initial image of the rear frame and the initial image of a front frame in sequence;
each time the initial image of the back frame and the initial image of the front frame are processed, the current kitchen oil smoke concentration at the moment when the initial image of the back frame is positioned is obtained by the following steps:
(1) Performing frame difference processing on the initial image of the rear frame and the initial image of the front frame to obtain a frame difference image;
(2) Denoising the frame difference image in an open operation mode to obtain a denoised image;
(3) Performing edge detection on the denoising image, and marking a motion region as an initial region of interest;
(4) Carrying out gray average value calculation and region smoothness calculation on an initial region of interest, taking a region meeting the requirements of gray average value and smoothness as a next region of interest, and taking other regions as interference elimination;
(5) And (3) respectively carrying out gray level histogram statistics on the interested areas extracted in the step (4), and dividing the oil smoke concentration level according to the statistical result.
In the step (1), the frame difference operation is performed on the acquired initial image to obtain a frame difference image specifically includes:
the visual detection module makes a difference between a next frame image and a previous frame image according to the sequence of the received initial images to obtain a frame difference image with a high brightness in a dynamic area;
preferably, the step (2) performs denoising processing on the frame difference image by adopting an open operation, so as to obtain a denoised image, and specifically performs the following steps: firstly, carrying out corrosion operation on the frame difference image to eliminate noise points and tiny spines in the image, and breaking narrow connection; and then expanding the corroded image to recover the smoke characteristics in the original frame difference image.
Preferably, the step (3) performs edge detection on the denoised image, and marks the motion region as an initial region of interest, specifically: and detecting the edge of the highlighted region of the frame difference image by utilizing wavelet transformation, marking, and taking the marked region as an initial region of interest.
Preferably, in the step (4), the gray average value and the region smoothness of each initial region of interest are calculated, so as to obtain the gray average value and the gray smoothness corresponding to each initial region of interest, the initial region of interest which meets the requirement that the calculated gray average value is smaller than the gray threshold value and the gray smoothness is smaller than the gray smoothness threshold value is taken as the region of interest, and other initial regions of interest are determined as the interference regions.
Preferably, in the step (5), gray histogram statistics is performed on the region of interest extracted in the step (4), and the oil smoke concentration level is classified according to the statistics result.
Counting the occurrence frequency of all pixels in the image of the region of interest according to the gray value;
and taking 10 as the interval length according to the number of concentration levels to be divided, and counting the number of pixel points in each gray scale interval, wherein the number of pixel points in each gray scale interval corresponds to the number of the divided oil smoke to be the corresponding concentration level.
The target area acquired by the imaging device is represented by an area S, and any frame of initial image is the imaging of the corresponding area S.
The initial image is made up of m x n pixels.
The gray values of the pixels of the initial image a of the subsequent frame are represented by a matrix AH, ah= { AH i,j }，ah i,j Representing gray values corresponding to the ith row and the jth column of pixels in the initial image A of the subsequent frame, wherein i is the row where the pixels are located, j is the column where the pixels are located, i is more than or equal to 1 and less than or equal to m, and j is more than or equal to 1 and less than or equal to n; the sub-area where the ith row and jth column pixels are located in the initial image A of the subsequent frame is AS i,j 。
The gray value of the pixel of the previous frame initial image B is represented by a matrix BH, bh= { BH i,j }，bh i,j Representing gray values corresponding to the ith row and the jth column pixels in the initial image B of the previous frame, wherein the subarea where the ith row and the jth column pixels are positioned in the initial image B of the previous frame is BS i,j 。
The pixel gray value of the frame difference image D is represented by a matrix DH, dh= { DH i,j }＝{ah i,j -bh i,j }，dh i,j Representing gray values corresponding to the ith row and the jth column pixels in the frame difference image D, wherein the subarea where the ith row and the jth column pixels in the frame difference image D are positioned is DS i,j 。
In the frame difference image, |dh i,j The region of |=0 is black; |dh i,j The region of i+.0 is highlighted.
And (3) performing corrosion operation on the frame difference image in the step (2), wherein the method specifically comprises the following steps of:
2-11, arbitrarily defining a convolution kernel theta;
2-12, convolving the convolution kernel theta with the frame difference image; when traversing the frame difference image by the convolution kernel theta, extracting a pixel gray minimum value p of a convolution result in the coverage area of the convolution kernel and a pixel point C overlapped with the center of the convolution kernel;
the gray level of the pixel point C passes through the matrix CH= { C k,q Represented by }, kQ is the row number and column number of pixel point C,
obtaining a minimum value pixel point matrix P of a convolution result obtained in the process of traversing the frame difference image by using a convolution kernel theta, wherein the gray level of the minimum value pixel point matrix P passes through a matrix PH= { P k,q -representation;
2-13, endowing the gray scale of the pixel point matrix P to the pixel point C correspondingly to obtain a corrosion image;
and (3) performing expansion operation on the corrosion image in the step (2), wherein the method specifically comprises the following steps of:
2-21, arbitrarily defining a convolution kernel beta;
2-22, convolving the convolution kernel beta with the corrosion image; when traversing the corrosion image by the convolution kernel beta, extracting a pixel gray maximum value o of a convolution result in the coverage area of the convolution kernel and a pixel point R overlapped with the center of the convolution kernel;
the gray level of the pixel point R passes through the matrix RH= { R l,v And indicates that l and v are the row number and column number of the pixel point R,
obtaining a convolution result maximum pixel point matrix O obtained in the process of traversing the convolution kernel beta through the corrosion image, wherein the gray level of the maximum pixel point matrix O passes through a matrix OH= { O l,v -representation;
and 2-13, endowing the gray scale of the maximum pixel point matrix O with the pixel point R correspondingly to obtain an expanded image, and obtaining the expanded image which is the denoising image.
Preferably, the step (3) is performed by the following steps:
3-1, defining a filter Y, wherein the filter is a t matrix, and t is an odd number;
3-2, traversing the filter Y through the denoising image, calculating the gray value of the denoising image of the central pixel point of each position of the filter and the gray values of other pixels in the neighborhood of the central pixel point, and calculating the center of the filter at each position according to the formula (I)Edge detection value X of pixel point z Z is the signature of filter Y as it traverses the denoised image,
f. g is the matrix serial number of the pixel points, f is not less than 1 and not more than t, g is not less than 1 and not more than t, and e is the gray value of the denoising image where the pixel point of the filter is positioned at each position; alpha is a weight coefficient and corresponds to the position of the filter;
3-3, the edge detection value X of the central pixel point of the filter at each position z Subtracting the gray values of other pixels in the neighborhood of the central pixel point, and judging whether the absolute value of the difference value is larger than a threshold delta;
counting a number greater than a threshold, if the number exceedsJudging the pixel point position of the denoising image corresponding to the central pixel point of the filter as an edge point, and marking;
3-4, traversing the complete denoising image by the filter to obtain all marked edge points, and obtaining a preliminary region of interest.
Preferably, t is 3.
The invention provides a lampblack concentration detection method which is different from an infrared projection method and a physical detection method. The oil smoke concentration detection method is hardly influenced by the detection distance, can realize non-contact real-time detection of the oil smoke concentration, and has the advantages of high accuracy, real-time performance and the like.
Drawings
The invention is further illustrated by the accompanying drawings, which are not to be construed as limiting the invention in any way.
Fig. 1 is a schematic cross-sectional view of a range hood with a visual detection module with a filtering function in embodiment 1.
Fig. 2 is an exploded schematic view of the visual inspection module.
Fig. 3 is an assembly schematic of fig. 2.
Fig. 4 is a schematic diagram of a range hood with a visual detection module with a filtering function in embodiment 2.
Fig. 5 is an exploded view of the visual inspection module of embodiment 4.
Fig. 6 is a schematic view of a soot region and an interference region divided by the method of the present invention.
In fig. 1 to 6, the method includes:
a visual detection module 1,
A filter part 11,
A visual detection unit 12,
Lens 121, expansion bracket 122, mounting base 123, photosensitive chip 124, PCB 125,
A light supplementing device 2,
A main body 3 of the cigarette making machine,
A stove 4.
Detailed Description
The technical scheme of the invention is further described with reference to the following examples.
Example 1.
As shown in fig. 1 to 3, the range hood with the optical filtering function visual detection module 1 is provided with a hood main body 3 and the visual detection module 1 for detecting the size of the oil smoke, wherein the visual detection module 1 is electrically connected with the hood main body 3.
The visual inspection module 1 is provided with a filter portion 11 for filtering visible light and a visual inspection portion 12, the filter portion 11 is assembled to the visual inspection portion 12, the visual inspection portion 12 is electrically connected with the range main body 3, and the visual inspection module 1 is directed to a corresponding range 4 area.
The light supplementing device is an infrared light supplementing device.
The range hood with the optical filtering function visual detection module 1 is further provided with a light supplementing device 2 for supplementing light to the area corresponding to the stove 4, the light supplementing device 2 is electrically connected with the range hood main body 3, and the light supplementing device 2 faces to the area corresponding to the stove 4.
The vision detection module 1 processes and sequences the collected initial images, and processes the initial images of the rear frames and the initial images of the front frames in sequence to obtain the current kitchen oil smoke concentration at the moment when the initial images of the rear frames are located. Meanwhile, the vision detection module 1 detects the kitchen oil smoke condition through an internal lens, and then the operation device of the vision detection module 1 obtains the current kitchen oil smoke concentration through an algorithm.
The light supplementing device 2 of the present invention is assembled in three ways, the first way is that the light supplementing device 2 is assembled on the main body 3 of the cigarette making machine. The second is that the light supplementing device 2 is assembled on the stove 4. The third is that the light supplementing device 2 is assembled on the wall, and the specific assembly mode of the light supplementing device 2 is determined according to the actual situation. In this embodiment, the light supplementing device 2 is mounted on the main body 3 of the cigarette making machine.
The visual inspection module 1 of the present invention is assembled in three ways, the first is that the visual inspection module 1 is assembled on the main body 3 of the cigarette making machine. The second is that the vision detecting module 1 is mounted to the stove 4. The third is that the visual inspection module 1 is assembled on the wall, and the specific assembly mode of the visual inspection module 1 is determined according to the actual situation. In this embodiment, the visual detection module 1 is mounted on the main body 3 of the cigarette making machine.
The filter unit 11 of the present invention is a visible light filter. The light supplementing device 2 is an infrared lamp group with the wavelength of 940 nm. A large number of experiments prove that the accuracy of detecting smoke is best when the visual detection module 1 with the wavelength of 940 nm.
The light supplementing device 2 of the invention is arranged as an infrared lamp set.
The vision detection module 1 processes and sequences the collected initial images, and processes the initial images of the rear frames and the initial images of the front frames in sequence to obtain the current kitchen oil smoke concentration at the moment of each initial image of the rear frames.
The vision detecting part 12 is provided with a lens 121, a telescopic frame 122 for setting a focal length, a mounting base 123, a photosensitive chip 124 and a PCB 125, the lens 121 is fixedly assembled on the telescopic frame 122, the telescopic frame 122 is assembled on the mounting base 123, the photosensitive chip 124 is welded on the PCB 125, the mounting base 123 is assembled on the PCB 125, the light filtering part 11 is assembled above the photosensitive chip 124, and the lens 121, the telescopic frame 122, the mounting base 123, the light filtering part 11, the photosensitive chip 124 and the PCB 125 are sequentially arranged from top to bottom.
It should be noted that, the photosensitive chip 124 of the present invention is common knowledge, and the photosensitive chip 124 of the present invention can be used as the photosensitive chip 124 as long as the function of capturing light and converting the light into an electronic signal is achieved, so the model of the photosensitive chip 124 is not described here.
The range hood with the optical filtering function visual detection module 1 is provided with a hood main body 3 and the visual detection module 1 for detecting the size of the oil smoke, wherein the visual detection module 1 is electrically connected with the hood main body 3; the visual detection module 1 is provided with a filtering part 11 for filtering visible light and a visual detection part 12, the filtering part 11 is assembled on the visual detection part 12, the visual detection part 12 is electrically connected with the smoke machine main body 3, and the visual detection module 1 faces to a corresponding range 4 area. The visual detection module 1 can filter visible light and perform light filling by adopting the light filling device 2, so that the interference problem caused by a natural light source and a stroboscopic light source can be eliminated, the visual detection module has a good effect on interference of shadows and the like, and meanwhile, the smoke size can be detected without turning on a lamp under bad lighting conditions such as cloudy days and the like.
Example 2.
As shown in fig. 4, the range hood with the optical filtering function vision detection module 1 has the other features similar to those of the embodiment 1, except that: the light supplementing device 2 is mounted on a wall, and the visual detection module 1 is mounted on the stove 4. The infrared lamp sets of the present invention are provided with a plurality of groups, and in this embodiment, 4 groups are specifically provided, and it should be noted that the infrared lamp sets of the present invention may be provided with 4 groups, or may be provided with any number greater than 2, and the specific implementation situation depends on the actual situation.
The present embodiment improves flexibility in the manner of assembling the visual inspection module 1 and the light supplementing device 2 as compared with embodiment 1.
Example 3.
As shown in fig. 5, the range hood with the optical filtering function visual detection module 1 has the other features same as those of the embodiment 1, except that: the vision detecting part 12 is provided with a lens 121, a telescopic frame 122 for setting a focal length, a mounting base 123, a photosensitive chip 124 and a PCB 125, the light filtering part 11 is assembled above the lens 121, the lens 121 is fixedly assembled on the telescopic frame 122, the telescopic frame 122 is assembled on the mounting base 123, the photosensitive chip 124 is welded on the PCB 125, the mounting base 123 is assembled on the PCB 125, and the light filtering part 11, the lens 121, the telescopic frame 122, the mounting base 123, the photosensitive chip 124 and the PCB 125 are sequentially assembled from top to bottom.
The filter unit 11 of the present embodiment is mounted above the visual inspection unit 12, so that the mounting flexibility of the filter unit 11 can be increased as compared with embodiment 1.
Example 4.
In the method for detecting the oil smoke concentration, a visual detection module 1 processes an initial image acquired by imaging equipment as a basis, the initial image is a gray level image, the acquired initial image is serialized, and the current kitchen oil smoke concentration at the moment when each initial image of a rear frame is positioned is obtained by processing the initial image of the rear frame and the initial image of a front frame in sequence. By the method, the oil smoke concentration condition of the current frame time can be obtained in real time, and even if the oil smoke concentration condition of the current frame image at each time is monitored according to the requirement, the method provides a basis for the automatic smoke pumping force of the range hood.
Each time the initial image of the back frame and the initial image of the front frame are processed, the current kitchen oil smoke concentration at the moment when the initial image of the back frame is positioned is obtained by the following steps:
(1) Performing frame difference processing on the initial image of the rear frame and the initial image of the front frame to obtain a frame difference image;
(2) Denoising the frame difference image in an open operation mode to obtain a denoised image;
(3) Performing edge detection on the denoising image, and marking a motion region as an initial region of interest;
(4) Carrying out gray average value calculation and region smoothness calculation on an initial region of interest, taking a region meeting the requirements of gray average value and smoothness as a next region of interest, and taking other regions as interference elimination;
(5) And (3) respectively carrying out gray level histogram statistics on the interested areas extracted in the step (4), and dividing the oil smoke concentration level according to the statistical result. The statistical method can be gray level histogram statistics, or other statistical methods can be selected.
In the step (1), the frame difference operation is performed on the acquired initial image to obtain a frame difference image specifically includes: the visual detection module 1 makes difference between the next frame image and the previous frame image according to the sequence of the received initial images, and obtains a frame difference image with a high dynamic area. Because the static area in the front and back frame images is unchanged, and the dynamic area (such as lampblack scattering, hand waving and the like) is changed, the static area is black after the frame difference, and the dynamic area appears as a highlight area with blurred edge after the frame difference, so that a frame difference image with highlight dynamic area can be obtained through the frame difference.
The target area acquired by the imaging equipment is represented by an area S, and any frame of initial image is the imaging of the corresponding area S; the initial image is made up of m x n pixels.
The gray values of the pixels of the initial image a of the subsequent frame are represented by a matrix AH, ah= { AH i,j }，ah i,j Representing gray values corresponding to the ith row and the jth column of pixels in the initial image A of the subsequent frame, wherein i is the row where the pixels are located, j is the column where the pixels are located, i is more than or equal to 1 and less than or equal to m, and j is more than or equal to 1 and less than or equal to n; the sub-area where the ith row and jth column pixels are located in the initial image A of the subsequent frame is AS i,j 。
The gray value of the pixel of the previous frame initial image B is represented by a matrix BH, bh= { BH i,j }，bh i,j Representing gray values corresponding to the ith row and the jth column pixels in the initial image B of the previous frame, wherein the subarea where the ith row and the jth column pixels are positioned in the initial image B of the previous frame is BS i,j 。
The pixel gray values of the frame difference image D are represented by a matrix DH,
DH＝{dh i,j }＝{ah i,j -bh i,j }，dh i,j representing gray values corresponding to the ith row and the jth column pixels in the frame difference image D, wherein the subarea where the ith row and the jth column pixels in the frame difference image D are positioned is DS i,j ；
In the frame difference image, |dh i,j The region of |=0 is black; |dh i,j The region of i+.0 is highlighted.
After the frame difference operation, step (2) is entered. Denoising the frame difference image by adopting open operation to obtain a denoised image, and specifically performing the following steps: firstly, carrying out corrosion operation on the frame difference image to eliminate noise points and tiny spines in the image, and breaking narrow connection; and then expanding the corroded image to recover the smoke characteristics in the original frame difference image.
And (3) performing corrosion operation on the frame difference image in the step (2), wherein the method specifically comprises the following steps of:
2-11, arbitrarily defining a convolution kernel theta;
2-12, convolving the convolution kernel theta with the frame difference image; when traversing the frame difference image by the convolution kernel theta, extracting a pixel gray minimum value p of a convolution result in the coverage area of the convolution kernel and a pixel point C overlapped with the center of the convolution kernel;
the gray level of the pixel point C passes through the matrix CH= { C k,q And k, q are the row number and column number of pixel C,
obtaining a minimum value pixel point matrix P of a convolution result obtained in the process of traversing the frame difference image by using a convolution kernel theta, wherein the gray level of the minimum value pixel point matrix P passes through a matrix PH= { P k,q -representation;
and 2-13, endowing the gray scale of the pixel point matrix P to the pixel point C correspondingly to obtain a corrosion image.
And (3) performing expansion operation on the corrosion image in the step (2), wherein the method specifically comprises the following steps of:
2-21, arbitrarily defining a convolution kernel beta;
2-22, convolving the convolution kernel beta with the corrosion image; when traversing the corrosion image by the convolution kernel beta, extracting a pixel gray maximum value o of a convolution result in the coverage area of the convolution kernel and a pixel point R overlapped with the center of the convolution kernel;
the gray level of the pixel point R passes through the matrix RH= { R l,v And indicates that l and v are the row number and column number of the pixel point R,
obtaining a convolution result maximum pixel point matrix O obtained in the process of traversing the convolution kernel beta through the corrosion image, wherein the gray level of the maximum pixel point matrix O passes through a matrix OH= { O l,v -representation;
and 2-13, endowing the gray scale of the maximum pixel point matrix O with the pixel point R correspondingly to obtain an expanded image, and obtaining the expanded image which is the denoising image.
The image noise can be eliminated by using the on operation, objects are separated at the slim points, the larger object boundary is smoothed, the area of the highlight area in the original image is basically unchanged, and the accuracy of the subsequent detection is not influenced.
And (3) performing edge detection on the denoising image, marking a motion region as an initial region of interest, and specifically: and detecting the edge of the highlighted region of the frame difference image by utilizing wavelet transformation, marking, and taking the marked region as an initial region of interest.
Because the gray value of the image edge and the gray value of the adjacent pixel point can generate larger gray value gradient, a filter is set according to the characteristic of the edge, and the filter is used for traversing the frame difference image. Step (3) is performed by the following steps:
3-1, defining a filter Y, the filter being a matrix of t x t, t being an odd number. The filter selects an odd matrix to ensure that there is only one center point, preferably a 3*3 matrix, and has the characteristic of small calculation amount.
3-2, traversing the filter Y through the denoising image, calculating the gray value of the denoising image of the central pixel point of each position of the filter and the gray values of other pixels in the neighborhood of the central pixel point, and calculating the edge detection value X of the central pixel point of each position of the filter according to the formula (I) z Z is the signature of filter Y as it traverses the denoised image,
f. g is the matrix serial number of the pixel points, f is not less than 1 and not more than t, g is not less than 1 and not more than t, and e is the gray value of the denoising image where the pixel point of the filter is positioned at each position; alpha is a weight coefficient corresponding to the filter position.
3-3, detecting the edge of the central pixel point of the filter at each positionValue X z Subtracting the gray values of other pixels in the neighborhood of the central pixel point, and judging whether the absolute value of the difference value is larger than a threshold delta;
counting a number greater than a threshold, if the number exceedsJudging the pixel point position of the denoising image corresponding to the central pixel point of the filter as an edge point, and marking;
3-4, traversing the complete denoising image by the filter to obtain all marked edge points, and obtaining a preliminary region of interest.
The difficulty of the invention is that the hand always swings when people do dishes, the images after the frame difference contain the interference areas of the moving objects such as oil smoke and human hand operation, and the influence of the interference areas needs to be removed before the oil smoke concentration identification is carried out.
However, the motion direction of the oil smoke has randomness, the motion direction of a human hand and a turner is relatively clear and different in characteristics, and the numerical expression is that the gray value difference is large, so that the method comprises the following steps:
1) The brightness of the oil smoke moving area on the image after the frame difference is lower than that of the human hand and the turner moving area, so that the gray value average value of the corresponding oil smoke area is also lower than that of the human hand and the turner moving area;
2) The gray value distribution of the oil smoke moving area on the image after the frame difference is concentrated, and the jump of the gray value of the boundary of the moving area of the human hand and the slice is larger than that of the central area of the area, so that the image of the area is not smooth enough, and the corresponding gray value variance is larger.
And (4) specifically, calculating the gray average value and the region smoothness of each initial region of interest by utilizing the two characteristics, obtaining the gray average value and the gray smoothness corresponding to each initial region of interest, taking the initial region of interest which simultaneously satisfies that the calculated gray average value is smaller than a gray threshold value and the gray smoothness is smaller than the gray smoothness threshold value as the region of interest, and judging other initial regions of interest as interference regions.
The magnitude of the gray level threshold and the gray level smoothness threshold can be flexibly set according to specific needs, and are not described herein. And (4) completing the identification of the oil smoke area and the removal of the interference area.
Fig. 6 illustrates a schematic diagram of a soot region and an interference region divided by the method of the present invention, and it can be seen that the method of the present invention can effectively exclude the interference region.
In the step (5), gray histogram statistics is respectively carried out on the interested areas extracted in the step (4), and the oil smoke concentration level is divided according to the statistical result, specifically:
counting the occurrence frequency of all pixels in the image of the region of interest according to the gray value;
and taking 10 as the interval length according to the number of concentration levels to be divided, and counting the number of pixel points in each gray scale interval, wherein the number of pixel points in each gray scale interval corresponds to the number of the divided oil smoke to be the corresponding concentration level.
The selection of the interval length is not limited to 10, and other numbers may be selected.
The dividing standard of the oil smoke concentration can be specifically set, for example, dense smoke, medium smoke or low smoke is set, and specific numerical values are based on actual requirements and are not described herein.
The invention provides a lampblack concentration detection method which is different from an infrared projection method and a physical detection method. The oil smoke concentration detection method is hardly influenced by the detection distance, can realize non-contact real-time detection of the oil smoke concentration, and has the advantages of high accuracy, real-time performance and the like.
The oil smoke concentration detection method can be arranged in the range hood, the imaging equipment arranged in the range hood is used for collecting images of a range area of the range hood and transmitting the images to the vision detection module 1, the vision detection module 1 is used for transmitting the processed oil smoke grade structure to the main control unit, and the main control unit is used for controlling the suction force of the range hood according to the oil smoke grade of the range hood. And the kitchen fume is pumped more accurately.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the scope of the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted equally without departing from the spirit and scope of the technical solution of the present invention.
Claims (14)
1. The utility model provides a lampblack absorber of utensil filtering capability vision detection module which characterized in that: the smoke machine is provided with a smoke machine main body and a visual detection module for detecting the size of the smoke, and the visual detection module is electrically connected with the smoke machine main body;
the visual detection module is provided with a filtering part for filtering visible light and a visual detection part, the filtering part is assembled on the visual detection part, the visual detection part is electrically connected with the main body of the smoke machine, and the visual detection module faces the corresponding stove area;
the visual detection module processes an initial image acquired by the imaging equipment as a basis, the initial image is a gray level image, the acquired initial image is serialized, and the current kitchen oil smoke concentration at the moment when each initial image of the rear frame is positioned is obtained by processing the initial image of the rear frame and the initial image of the front frame in sequence;
each time the initial image of the back frame and the initial image of the front frame are processed, the current kitchen oil smoke concentration at the moment when the initial image of the back frame is positioned is obtained by the following steps:
(1) Performing frame difference processing on the initial image of the rear frame and the initial image of the front frame to obtain a frame difference image;
(2) Denoising the frame difference image in an open operation mode to obtain a denoised image;
(3) Performing edge detection on the denoising image, and marking a motion region as an initial region of interest;
(4) Carrying out gray average value calculation and region smoothness calculation on an initial region of interest, taking a region meeting the requirements of gray average value and smoothness as a next region of interest, and taking other regions as interference elimination;
(5) And (3) respectively carrying out gray level histogram statistics on the interested areas extracted in the step (4), and dividing the oil smoke concentration level according to the statistical result.
2. The range hood with the optical filtering function visual detection module according to claim 1, wherein: the light supplementing device is electrically connected with the main body of the smoke machine, and the light supplementing device faces the corresponding stove area.
3. The range hood with the optical filtering function visual detection module according to claim 2, wherein: the light supplementing device is an infrared light supplementing device.
4. The range hood with the optical filtering function visual detection module according to claim 3, wherein: the visual detection module is assembled on the main body of the cigarette machine; or alternatively
The visual detection module is assembled on the stove; or alternatively
The visual detection module is assembled on the wall body.
5. The range hood with the optical filtering function visual detection module according to claim 4, wherein: the light supplementing device is assembled on the main body of the cigarette machine; or alternatively
The light supplementing device is assembled on the stove; or alternatively
The light supplementing device is assembled on the wall body.
6. The range hood with the optical filtering function visual detection module according to claim 5, wherein: the light filtering part is a visible light filter.
7. The range hood with the optical filtering function visual detection module according to claim 6, wherein: the light supplementing device is an infrared lamp group with the wavelength of 940 nm.
8. The range hood with the optical filtering function visual detection module according to claim 7, wherein: the light supplementing device is arranged as an infrared lamp group.
9. The range hood with the optical filtering function visual detection module according to claim 8, wherein: the visual detection module processes and sequences the acquired initial images, and processes the initial images of the rear frames and the initial images of the front frames in sequence to obtain the current kitchen oil smoke concentration at the moment of each initial image of the rear frames;
the infrared lamp sets are provided with a plurality of groups.
10. The range hood with the optical filtering function visual detection module according to claim 9, wherein: the visual inspection portion is provided with the camera lens, be used for setting up expansion bracket, installation base, sensitization chip and the PCB board of focus, camera lens fixed mounting in the expansion bracket, and the expansion bracket is assembled in the installation base, and sensitization chip welds in the PCB board, and the installation base is assembled in the PCB board, and the optical filter portion is assembled in the top of sensitization chip, from last camera lens, expansion bracket, installation base, optical filter portion, sensitization chip and the PCB board down in proper order.
11. The range hood with the optical filtering function visual detection module according to claim 9, wherein: the visual inspection portion is provided with the camera lens, be used for setting up expansion bracket, installation base, sensitization chip and the PCB board of focus, and the optical filtering portion is assembled in the top of camera lens, and camera lens fixed assembly is in the expansion bracket, and the expansion bracket is assembled in the installation base, and sensitization chip welds in the PCB board, and the installation base is assembled in the PCB board, from last optical filtering portion, camera lens, expansion bracket, installation base, sensitization chip and the PCB board down in proper order.
12. The method for detecting the oil smoke concentration is characterized in that the range hood with the optical filtering function visual detection module is provided with the characteristics according to any one of claims 1 to 11, the visual detection module processes the initial image collected by imaging equipment as a basis, the initial image is a gray level image, the collected initial image is serialized, and the current kitchen oil smoke concentration at the moment when each initial image of the back frame is positioned is obtained by processing the initial image of the back frame and the initial image of the front frame in sequence;
each time the initial image of the back frame and the initial image of the front frame are processed, the current kitchen oil smoke concentration at the moment when the initial image of the back frame is positioned is obtained by the following steps:
(1) Performing frame difference processing on the initial image of the rear frame and the initial image of the front frame to obtain a frame difference image;
(2) Denoising the frame difference image in an open operation mode to obtain a denoised image;
(3) Performing edge detection on the denoising image, and marking a motion region as an initial region of interest;
(4) Carrying out gray average value calculation and region smoothness calculation on an initial region of interest, taking a region meeting the requirements of gray average value and smoothness as a next region of interest, and taking other regions as interference elimination;
(5) And (3) respectively carrying out gray level histogram statistics on the interested areas extracted in the step (4), and dividing the oil smoke concentration level according to the statistical result.
13. The method for detecting the concentration of oil smoke according to claim 12, wherein in the step (1), the frame difference operation is performed on the collected initial image to obtain a frame difference image specifically comprises:
the visual detection module makes a difference between a next frame image and a previous frame image according to the sequence of the received initial images to obtain a frame difference image with a high brightness in a dynamic area;
and (2) denoising the frame difference image by adopting open operation to obtain a denoised image, wherein the denoising method is specifically carried out in the following mode: firstly, carrying out corrosion operation on the frame difference image to eliminate noise points and tiny spines in the image, and breaking narrow connection; then expanding the corroded image to recover the smoke characteristics in the original frame difference image;
the step (3) is to carry out edge detection on the denoising image, mark a motion area as an initial interested area, and specifically comprises the following steps: detecting the edge of the highlight region of the frame difference image by utilizing wavelet transformation, marking, and taking the marked region as an initial region of interest;
the step (4) is specifically to calculate the gray average value and the region smoothness of each initial region of interest to obtain the gray average value and the gray smoothness corresponding to each initial region of interest, and the initial region of interest which simultaneously satisfies the calculation that the gray average value is smaller than the gray threshold value and the gray smoothness is smaller than the gray smoothness threshold value is used as the region of interest, and other initial regions of interest are determined as interference regions;
in the step (5), gray histogram statistics is performed on the region of interest extracted in the step (4), and the oil smoke concentration level is divided according to the statistics result, specifically:
counting the occurrence frequency of all pixels in the image of the region of interest according to the gray value;
and taking 10 as the interval length according to the number of concentration levels to be divided, and counting the number of pixel points in each gray scale interval, wherein the number of pixel points in each gray scale interval corresponds to the number of the divided oil smoke to be the corresponding concentration level.
14. The method for detecting the concentration of oil smoke according to claim 13, wherein the target area acquired by the imaging device is represented by an area S, and any one frame of initial image is an image of the corresponding area S;
the initial image is made up of m x n pixels,
the gray values of the pixels of the initial image a of the subsequent frame are represented by a matrix AH, ah= { AH i,j }，ah i,j Representing gray values corresponding to the ith row and the jth column of pixels in the initial image A of the subsequent frame, wherein i is the row where the pixels are located, j is the column where the pixels are located, i is more than or equal to 1 and less than or equal to m, and j is more than or equal to 1 and less than or equal to n; the sub-area where the ith row and jth column pixels are located in the initial image A of the subsequent frame is AS i,j ；
The gray value of the pixel of the previous frame initial image B is represented by a matrix BH, bh= { BH i,j }，bh i,j Representing gray values corresponding to the ith row and the jth column pixels in the initial image B of the previous frame, wherein the subarea where the ith row and the jth column pixels are positioned in the initial image B of the previous frame is BS i,j ；
The pixel gray value of the frame difference image D is represented by a matrix DH, dh= { DH i,j }＝{ah i,j -bh i,j }，dh i,j Representing gray values corresponding to the ith row and the jth column pixels in the frame difference image D, wherein the subarea where the ith row and the jth column pixels in the frame difference image D are positioned is DS i,j ；
In the frame difference image, |dh i,j The region of |=0 is black; |dh i,j The region with the intensity not equal to 0 is highlighted;
and (3) performing corrosion operation on the frame difference image in the step (2), wherein the method specifically comprises the following steps of:
2-11, arbitrarily defining a convolution kernel theta;
2-12, convolving the convolution kernel theta with the frame difference image; when traversing the frame difference image by the convolution kernel theta, extracting a pixel gray minimum value p of a convolution result in the coverage area of the convolution kernel and a pixel point C overlapped with the center of the convolution kernel;
the gray level of the pixel point C passes through the matrix CH= { C k,q And k, q are the row number and column number of pixel C,
obtaining a minimum value pixel point matrix P of a convolution result obtained in the process of traversing the frame difference image by using a convolution kernel theta, wherein the gray level of the minimum value pixel point matrix P passes through a matrix PH= { P k,q -representation;
2-13, endowing the gray scale of the pixel point matrix P to the pixel point C correspondingly to obtain a corrosion image;
and (3) performing expansion operation on the corrosion image in the step (2), wherein the method specifically comprises the following steps of:
2-21, arbitrarily defining a convolution kernel beta;
2-22, convolving the convolution kernel beta with the corrosion image; when traversing the corrosion image by the convolution kernel beta, extracting a pixel gray maximum value o of a convolution result in the coverage area of the convolution kernel and a pixel point R overlapped with the center of the convolution kernel;
the gray level of the pixel point R passes through the matrix RH= { R l,v And indicates that l and v are the row number and column number of the pixel point R,
obtaining a convolution result maximum pixel point matrix O obtained in the process of traversing the convolution kernel beta through the corrosion image, wherein the gray level of the maximum pixel point matrix O passes through a matrix OH= { O l,v -representation;
2-13, endowing the gray scale of the maximum pixel point matrix O with a pixel point R correspondingly to obtain an expanded image, wherein the obtained expanded image is a denoising image;
the step (3) is carried out by the following steps:
3-1, defining a filter Y, wherein the filter is a t matrix, and t is an odd number;
3-2, traversing the filter Y through the denoising image, calculating the gray value of the denoising image of the central pixel point of each position of the filter and the gray values of other pixels in the neighborhood of the central pixel point, and calculating the edge detection value X of the central pixel point of each position of the filter according to the formula (I) z Z is the signature of filter Y as it traverses the denoised image,
f. g is the matrix serial number of the pixel points, f is not less than 1 and not more than t, g is not less than 1 and not more than t, and e is the gray value of the denoising image where the pixel point of the filter is positioned at each position; alpha is a weight coefficient and corresponds to the position of the filter;
3-3, the edge detection value X of the central pixel point of the filter at each position z Subtracting the gray values of other pixels in the neighborhood of the central pixel point, and judging whether the absolute value of the difference value is larger than a threshold delta;
counting a number greater than a threshold, if the number exceedsJudging the pixel point position of the denoising image corresponding to the central pixel point of the filter as an edge point, and marking;
3-4, traversing the complete denoising image by using the filter to obtain all marked edge points and obtaining a preliminary region of interest;
and t is 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811151666.1A CN109084350B (en) | 2018-09-29 | 2018-09-29 | Range hood with optical filtering function visual detection module and range hood concentration detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811151666.1A CN109084350B (en) | 2018-09-29 | 2018-09-29 | Range hood with optical filtering function visual detection module and range hood concentration detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109084350A CN109084350A (en) | 2018-12-25 |
| CN109084350B true CN109084350B (en) | 2024-01-09 |
Family
ID=64843025
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811151666.1A Active CN109084350B (en) | 2018-09-29 | 2018-09-29 | Range hood with optical filtering function visual detection module and range hood concentration detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109084350B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109738582B (en) * | 2018-12-29 | 2021-11-23 | 佛山市云米电器科技有限公司 | Kitchen ambient air quality prompting device |
| CN109884049B (en) * | 2018-12-29 | 2023-06-16 | 佛山市云米电器科技有限公司 | Harmful substance detection device capable of detecting kitchen fume |
| CN109632796B (en) * | 2018-12-29 | 2023-06-16 | 佛山市云米电器科技有限公司 | Harmful substance detection equipment with infrared temperature sensor and application thereof |
| CN109657640A (en) * | 2018-12-29 | 2019-04-19 | 佛山市云米电器科技有限公司 | It is a kind of can according to use food materials carry out Health Category division kitchen ventilator |
| CN109654560A (en) * | 2018-12-29 | 2019-04-19 | 佛山市云米电器科技有限公司 | It is a kind of can according to use oils carry out kitchen air quality assessment kitchen ventilator |
| CN109813841B (en) * | 2018-12-29 | 2021-11-23 | 佛山市云米电器科技有限公司 | Kitchen oil smoke formula polycyclic aromatic hydrocarbon detection device |
| CN110907321A (en) * | 2019-12-05 | 2020-03-24 | 东莞理工学院 | Lampblack absorber oil smoke concentration visual detection system with visible light filtering function |
| CN113188165B (en) * | 2020-01-14 | 2022-08-12 | 宁波方太厨具有限公司 | Cooking fume exhauster |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102814574A (en) * | 2012-09-06 | 2012-12-12 | 江苏科技大学 | Narrow gap welding monitoring and welding line deviation detecting method based on infrared vision sensing |
| CN104102163A (en) * | 2013-04-15 | 2014-10-15 | 无锡中科水质环境技术有限公司 | Kitchen detection control system |
| CN107702174A (en) * | 2017-11-07 | 2018-02-16 | 佛山市云米电器科技有限公司 | Oil smoke tracing system and method |
| CN107796328A (en) * | 2017-09-21 | 2018-03-13 | 西南交通大学 | Metal increasing material manufacturing Pool three-dimensional visual sensor and detection method |
| CN108534196A (en) * | 2018-03-08 | 2018-09-14 | 佛山市云米电器科技有限公司 | The cooking apparatus and its interlock method of noise reduction system and vision detection system linkage |
| CN108549305A (en) * | 2018-03-08 | 2018-09-18 | 佛山市云米电器科技有限公司 | A kind of anti-dry method of view-based access control model identification, cooking apparatus |
| CN209013288U (en) * | 2018-09-29 | 2019-06-21 | 佛山市云米电器科技有限公司 | A kind of kitchen ventilator having filtering functions vision-based detection module |
-
2018
- 2018-09-29 CN CN201811151666.1A patent/CN109084350B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102814574A (en) * | 2012-09-06 | 2012-12-12 | 江苏科技大学 | Narrow gap welding monitoring and welding line deviation detecting method based on infrared vision sensing |
| CN104102163A (en) * | 2013-04-15 | 2014-10-15 | 无锡中科水质环境技术有限公司 | Kitchen detection control system |
| CN107796328A (en) * | 2017-09-21 | 2018-03-13 | 西南交通大学 | Metal increasing material manufacturing Pool three-dimensional visual sensor and detection method |
| CN107702174A (en) * | 2017-11-07 | 2018-02-16 | 佛山市云米电器科技有限公司 | Oil smoke tracing system and method |
| CN108534196A (en) * | 2018-03-08 | 2018-09-14 | 佛山市云米电器科技有限公司 | The cooking apparatus and its interlock method of noise reduction system and vision detection system linkage |
| CN108549305A (en) * | 2018-03-08 | 2018-09-18 | 佛山市云米电器科技有限公司 | A kind of anti-dry method of view-based access control model identification, cooking apparatus |
| CN209013288U (en) * | 2018-09-29 | 2019-06-21 | 佛山市云米电器科技有限公司 | A kind of kitchen ventilator having filtering functions vision-based detection module |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109084350A (en) | 2018-12-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109084350B (en) | Range hood with optical filtering function visual detection module and range hood concentration detection method | |
| CN109816678B (en) | Automatic nozzle atomization angle detection system and method based on vision | |
| CN103714345B (en) | A kind of method and system of binocular stereo vision detection finger fingertip locus | |
| JP4611776B2 (en) | Image signal processing device | |
| CN105915840B (en) | A method of the factory smoke discharge based on vision signal monitors automatically | |
| CN108760590B (en) | Kitchen oil smoke concentration detection and interference elimination method based on image processing | |
| JP4542929B2 (en) | Image signal processing device | |
| CN107610085A (en) | A kind of welding point defect detecting system based on computer vision | |
| CN109028223B (en) | Range hood with gesture control visual detection function and range hood concentration detection method | |
| CN109579092B (en) | Range hood capable of realizing linkage of smoke range according to working environment | |
| CN109028230A (en) | Have the stove and oil smoke concentration detection method of gesture control vision-based detection function | |
| JP4491360B2 (en) | Image signal processing device | |
| CN109682326A (en) | Pot seedling upright degree detection device and detection method based on depth image | |
| CN109344827B (en) | Range hood with light supplementing device and range hood concentration detection method | |
| CN110413143B (en) | Man-machine interaction method based on laser radar | |
| CN109028231A (en) | A kind of the cigarette stove all-in-one machine and oil smoke concentration detection method of view-based access control model gesture control | |
| CN109089032A (en) | A kind of smog vision imaging device | |
| CN109389075B (en) | Intelligent smoke machine lens fuzzy self-checking method | |
| CN209013288U (en) | A kind of kitchen ventilator having filtering functions vision-based detection module | |
| CN109028224A (en) | A kind of kitchen ventilator and oil smoke concentration detection method having light self-adaptive visual function | |
| CN109738582B (en) | Kitchen ambient air quality prompting device | |
| CN109373377A (en) | A kind of kitchen ventilator and oil smoke concentration detection method with fixed vision detection system | |
| CN109142176B (en) | Smoke subarea space rechecking method based on space association | |
| CN209229817U (en) | A kind of kitchen ventilator with Shockproof type vision-based detection module | |
| CN209101364U (en) | A kind of kitchen ventilator with light compensating apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |